Neural networks come in a wide range of shapes and functions, with diverse architectures and parameters for input, hidden and output nodes as well as convolutive or recurrent nodes.
Regrouped in a convenient summary by Fjodor Van Veen, the most popular architectures for neural networks have been cataloged with detailed descriptions for each type of neural network. The complete post with explanations on the use and goals of each network can be be found on the Asimov Institute “the neural network zoo“.
TensorFlow is an open-source machine learning framework developed by Google. It relies upon Tensors (multi-dimensional arrays) which empower a wide range of API to develop machine learning applications, primarily deep neural networks. TensorFlow is commonly used in machine learning practice, so better start using it already.
Thankfully the TensorFlow website provides a guide for programmers as well as detailed tutorials. Here is the basic tutorial to get get started with TensorFlow. To accompany programmers, Google cloud has also created a series of videos on machine learning and TensorFlow.
This next video is going over the basic tutorial with iris flowers images classification. Yufeng Guo walks us through the initial tutorial to develop a linear model to classify flowers, corresponding to the explanations and code available in the page “getting started with TensorFlow: Premade Estimators” and aimed at readers who have some experience in machine learning.
Note: to get this tutorial running well, you will need to have a Python IDE (such as PyCharm, or a Jupyter notebook) with a virtual environment loaded with the TensorFlow, Pandas and Numpy librairies. You will also need a Git client software (Git for Windows if you’re using Windows) to download the data from GitHub. You may use Anaconda to properly load the librairies in your Python IDE.
Though neural networks were considered to be of little use for a long time, the recent development of computing power and database size has proven otherwise. Since the revolution of machine learning in the last few years has been primarily driven by them, let’s dive right into the actual coding of neural nets.
Before coding, it can be useful to review the principles of neural nets to make sure we understand what we will be doing here. Thankfully, the work of coding has already been done by Milo Spencer-Harper, based upon the previous works of Andrew Trask. He guides us step by step into building a single-layer neural net and multiple-layer neural net, with crystal-clear coding and without using any machine learning library.
Since a single-layer neural net is of little use and the problem it solves can better be achieved through other methods, it is included here as a didactic step to better understand and learn to code multiple-layer neural nets.
In these two example, the complexity of the problem, and therefore the number of layers needed to solved it, consists in the number of columns of data to be taken into account. The single layer neural network solves the problem when one column of data is critical, the multiple-layers neural net (2 layers) when two columns are critical.
Single-layer neural net
In the first post, the building of a simple neural network is detailed through the following key steps synthesized here. The data set is a 3 columns matrix where only one column affects the results. The single layer neural net is used to understand the direct influence this single column of data over the result.
Training data: Only the first column of input impacts the output
Since the code has been written in a previous version of Python, here are also included fully functional updated version for Python 3.6. Here is the light 9-line initial code for the single layer neural network.
Take inputs, adjust with weights (positive or negative numbers), norm them through a sigmoid function
Calculate the error between the neuron’s output and the actual training data set
Adjust weights according to the error
Repeat 10,000 times
Calculate the neuron’s output
Sum the weighted input data into a sigmoid function to obtain normed results in the interval ]0;1[
The final formula for the output of the neuron is:
Use the error weighted derivative = gradient descent
The neuron output from the sigmoid function indicates that if the output is close to 0 or 1, the data was close to the expected result
Close to 0 or 1, the derivative of the sigmoid function is almost flat
The adjustment to the weights based upon the derivative from the sigmoid function will therefore be very small when the neuron’s output is close to expected results or large when results differ from expectations
The sigmoid derivative equation is:
So the final equation to adjust weights is:
Here is a fully functional version of the final code for the single-layer neural network with all details and comments, updated for Python 3.6.
Multiple-layer neural net
In the second post, the building of a multiple neural network is detailed through the following key steps reproduced. Bear in mind that such a neural network may be to complicated to solve simple problems and that it is best to understand nonlinear patterns, where the second layer of neurons can take combination of data inputs into account.
Here this two-layer neural net is used to understand how two columns in the data influence the results.
Training data: The two first columns of input impact the output (XOR gate)
As Milo Spencer-Harper reminds us in his article, multiple layers are the source of the revolution in machine learning and artificial intelligence:
The process of adding more layers to a neural network, so it can think about combinations, is called deep learning.
The main difference in the code from the single-layer neural net is that the two layers influence the calculations for the error, and therefore the adjustment of weights. The errors from the second layer of neurons need to be propagated backwards to the first layer, this is called backpropagation.
Here is a fully functional version of the code for a two-layer neural network with all details and comments, updated for Python 3.6.
To sum up, in the following video, Siraj Raval goes over the detailed programming of a similar neural net (the original from Andrew Trask) in 4 minutes.
Attention: he uses an older version of Python, he also builds a 3-layer neural net, but the first layer is actually the input data without computation.
Though several programming languages can be used to develop Artificial Intelligence applications, the language that is most often used and advised to use is Python, because it is a general purpose language designed for readability.
Documentation and resources can be found to use and learn the language on the official Python website, especially with the complete tutorial available for each version of Python.
If you already have programming experience, you can have a brief overview of the syntax and specificity of Python in this video. This great course on problem-solving with algorithms and data structures will give you a complete, step-by-step approach to learning Python with explanations, videos and exercises, while this other tutorial from Stanford quickly goes over Python basics but dives deeper into using the Numpy, SciPy and Matplotlib modules for scientific computing.
Other languages that are often used include: Java, Lisp, Prolog, C++, R…
Python Programming Tools
Here is a series of programming tools and other systems to assist in the programming of AI applications.
PyCharm: an Integrated Development Environment – IDE – used in computer programming, specifically for the Python language.
Jupyter: the Jupyter Notebook is an open-source web application to create and share documents with live code, equations, visualizations.
NumPy is the fundamental package for scientific computing with Python.
TensorFlow: an open-source machine learning framework originally developed by Google Brain researchers and engineers.
Anaconda: Anaconda is a platform for Python and R data science and machine learning on Linux, Windows, and Mac OS X.
TFLearn: a deep learning library featuring a higher-level API for TensorFlow
Scikit-Learn: an open-source machine learning library for Python
Pandas: open-source data structure and analysis library for Python
Caffe: a deep learning framework made with expression, speed, and modularity in mind
Keras: a high-level neural networks API, written in Python
Pytorch: an open source machine learning library for Python, used for applications such as natural language processing.
Certain AI applications may require large computing power to process important amounts of data. Fortunately, several companies provide such services on a regular or on-demand basis. Here are the most famous cloud computing services.
In this post are gathered the tutorials and exercises, called “mega-recitations”, to apply the concepts presented in the Artificial Intelligence course of Prof. Patrick Winston. Continue reading “24. Reviews and Exercises”